Abstract
This paper develops an enhanced teaching interface tested on both a Baxter robot and a KUKA iiwa robot. Movements are collected from a human demonstrator by using a Kinect v2 sensor, and then the data is sent to a remote PC for the teleoperation with Baxter. Meanwhile, data is saved locally for the playback process of the Baxter. The dynamic movement primitive (DMP) is used to model and generalize the movements. In order to learn from multiple demonstrations accurately, dynamic time warping (DTW), is used to pretreat the data recorded by the robot platform and Gaussian mixture model (GMM), aiming to generate multiple patterns after the teaching process, are employed for the calculation of the DMP. Then the Gaussian mixture regression (GMR) algorithm is applied to generate a synthesized trajectory with smaller position errors in 3D space. This proposed approach is tested by performing two tasks on a KUKA iiwa and a Baxter robot.
Highlights
With the advance of new robotic technology, the application of robots in both industry and social service fields has been widely used
A Gaussian mixture regression (GMR) and dynamic movement primitive (DMP) combined with dynamic time warping (DTW) based teaching by demonstration technology has been developed in this paper, which is an effective and superior method for humans to interact with the robot
The discrete DMP is selected as the basic motion model, which can achieve the generalization of the motions
Summary
With the advance of new robotic technology, the application of robots in both industry and social service fields has been widely used. The teaching process from a human operator transfers the motor skills to the imitator (robot) through recording the motion of the learning movement and generalized output Calinon et al (2014). Gaussian mixture model (GMM) is a commonly used clustering algorithm The dynamic movement primitive (DMP) is used to model and generalize the motion trajectory inside the obstacle environment via combining the specific planning algorithm with its generalization and anti-jamming. A KUKA iiwa robot has been used to prove the achievement of our designed teaching method by drawing curves in a horizontal flat paper programming by recording a sequence of actions taught by a human demonstrator, after that we use the DTW and GMR to analyse and generalize the recorded movements. The robot could playback in the vertical plan, which shows the success of our developed teaching interface
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Intelligent Robotics and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
